DreadMix
DreadMix is a merge of the following models using LazyMergekit:
🧩 Configuration
models:
- model: DreadPoor/Aurora_faustus-8B-LORABLATED_ALT
- model: DreadPoor/Eunoia_Vespera-8B-LINEAR
parameters:
density: 0.53
weight: 0.55
- model: DreadPoor/Promissum_Mane-8B-LINEAR-lorablated
parameters:
density: 0.53
weight: 0.45
merge_method: dare_ties
base_model: DreadPoor/Aurora_faustus-8B-LORABLATED_ALT
parameters:
int8_mask: true
dtype: bfloat16
💻 Usage
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "BoltMonkey/DreadMix"
messages = [{"role": "user", "content": "What is a large language model?"}]
tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
"text-generation",
model=model,
torch_dtype=torch.float16,
device_map="auto",
)
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 28.46 |
| IFEval (0-Shot) | 70.95 |
| BBH (3-Shot) | 34.85 |
| MATH Lvl 5 (4-Shot) | 13.75 |
| GPQA (0-shot) | 6.60 |
| MuSR (0-shot) | 13.62 |
| MMLU-PRO (5-shot) | 31.00 |